3 papers
cs.LG2025
Homophily-aware Heterogeneous Graph Contrastive Learning
Haosen Wang, Chenglong Shi, Can Xu +2
Heterogeneous graph pre-training (HGP) has demonstrated remarkable performance across various domains. However, the issue of heterophily in real-world heterogeneous graphs (HGs) ha…
cs.LG2024
Diffusion-based Graph Generative Methods
Hongyang Chen, Can Xu, Lingyu Zheng +2
Being the most cutting-edge generative methods, diffusion methods have shown great advances in wide generation tasks. Among them, graph generation attracts significant research att…
cs.LG2024
Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
Can Xu, Haosen Wang, Weigang Wang +2
Denoising diffusion models have shown great potential in multiple research areas. Existing diffusion-based generative methods on de novo 3D molecule generation face two major chall…